conductor(plan): add state.toml for tier2_autonomous_sandbox track

44 tasks across 9 phases, all pending. Tracks:
- failcount unit test progression (13 target)
- slash command spec tests (11 target)
- report writer tests (4 opt-in)
- bootstrap test (1 opt-in)
- sandbox enforcement test (1 opt-in)
- smoke e2e test (1 opt-in, double gate)

Enforcement stack contract: 9 flags tracking the 4 git bans + filesystem
boundary + 3 hook installs + OpenCode deny rules + Windows restricted token.
Final verification requires all 9 enforcement flags = true.

status: active, current_phase: 0, blocked_by: none, blocks: none
This commit is contained in:
ed
2026-06-16 18:51:42 -04:00
parent 2551ff18c7
commit e060399579
@@ -0,0 +1,132 @@
# Track state for tier2_autonomous_sandbox_20260616
# Updated by Tier 2 Tech Lead as tasks complete
[meta]
track_id = "tier2_autonomous_sandbox_20260616"
name = "Tier 2 Autonomous Sandbox (unattended track execution with bounded blast radius)"
status = "active"
current_phase = 0
last_updated = "2026-06-16"
[blocked_by]
# None - independent track (per spec §1.1)
[blocks]
# None - this is a meta-tooling track; no follow-ups planned in this spec
[phases]
phase_1 = { status = "pending", checkpointsha = "", name = "failcount Module + Tests (TDD red/green)" }
phase_2 = { status = "pending", checkpointsha = "", name = "Failure Report Writer" }
phase_3 = { status = "pending", checkpointsha = "", name = "Slash Command + Agent Profile + Spec Test" }
phase_4 = { status = "pending", checkpointsha = "", name = "CLI Entry Point (run_track.py)" }
phase_5 = { status = "pending", checkpointsha = "", name = "PowerShell Bootstrap (setup_tier2_clone.ps1)" }
phase_6 = { status = "pending", checkpointsha = "", name = "PowerShell Sandbox Launcher (run_tier2_sandboxed.ps1)" }
phase_7 = { status = "pending", checkpointsha = "", name = "Git Hooks" }
phase_8 = { status = "pending", checkpointsha = "", name = "Opt-in Tests (Sandbox Enforcement + Smoke E2E)" }
phase_9 = { status = "pending", checkpointsha = "", name = "User Guide + Final Verification" }
[tasks]
# Phase 1: failcount Module + Tests
t1_1 = { status = "pending", commit_sha = "", description = "Create the scripts/tier2/ package directory" }
t1_2 = { status = "pending", commit_sha = "", description = "Write test_initial_state_zero (red)" }
t1_3 = { status = "pending", commit_sha = "", description = "Implement FailcountState + FailcountConfig dataclasses (green)" }
t1_4 = { status = "pending", commit_sha = "", description = "Create the default failcount.toml" }
t1_5 = { status = "pending", commit_sha = "", description = "Write test_red_phase_failure_increments (red)" }
t1_6 = { status = "pending", commit_sha = "", description = "Implement record_red_failure (green)" }
t1_7 = { status = "pending", commit_sha = "", description = "Write + implement test_green_success_resets_red_counter" }
t1_8 = { status = "pending", commit_sha = "", description = "Write + implement test_green_phase_failure_increments" }
t1_9 = { status = "pending", commit_sha = "", description = "Write + implement test_no_progress_advances" }
t1_10 = { status = "pending", commit_sha = "", description = "Write + implement test_no_progress_resets_on_commit and test_no_progress_resets_on_green" }
t1_11 = { status = "pending", commit_sha = "", description = "Write + implement test_threshold_fires_at_three and test_threshold_does_not_fire_at_two" }
t1_12 = { status = "pending", commit_sha = "", description = "Write + implement test_multi_signal_independence and test_any_signal_triggers" }
t1_13 = { status = "pending", commit_sha = "", description = "Write + implement test_state_persistence_round_trip" }
t1_14 = { status = "pending", commit_sha = "", description = "Write + implement test_configurable_thresholds" }
t1_15 = { status = "pending", commit_sha = "", description = "Implement load_state and save_state with atomic write" }
t1_16 = { status = "pending", commit_sha = "", description = "Verify 100% coverage on failcount.py + User Manual Verification" }
# Phase 2: Failure Report Writer
t2_1 = { status = "pending", commit_sha = "", description = "Write test_report_path_is_correct (red)" }
t2_2 = { status = "pending", commit_sha = "", description = "Implement compute_report_path, compute_stopped_flag_path, TaskResult (green)" }
t2_3 = { status = "pending", commit_sha = "", description = "Write test_report_has_7_sections (red)" }
t2_4 = { status = "pending", commit_sha = "", description = "Implement write_failure_report with 7 sections + flag (green)" }
# Phase 3: Slash Command + Agent Profile + Spec Test
t3_1 = { status = "pending", commit_sha = "", description = "Create the tier-2-auto-execute.md slash command template" }
t3_2 = { status = "pending", commit_sha = "", description = "Create the tier2-autonomous.md agent template" }
t3_3 = { status = "pending", commit_sha = "", description = "Create the opencode.json.fragment config template" }
t3_4 = { status = "pending", commit_sha = "", description = "Write test_tier2_slash_command_spec.py (11 contract assertions)" }
t3_5 = { status = "pending", commit_sha = "", description = "User Manual Verification (Phase 3)" }
# Phase 4: CLI Entry Point (run_track.py)
t4_1 = { status = "pending", commit_sha = "", description = "Create run_track.py skeleton with argparse" }
t4_2 = { status = "pending", commit_sha = "", description = "Wire in git fetch + branch creation" }
t4_3 = { status = "pending", commit_sha = "", description = "User Manual Verification (Phase 4)" }
# Phase 5: PowerShell Bootstrap (setup_tier2_clone.ps1)
t5_1 = { status = "pending", commit_sha = "", description = "Create the bootstrap script skeleton with -WhatIf" }
t5_2 = { status = "pending", commit_sha = "", description = "User Manual Verification (Phase 5)" }
# Phase 6: PowerShell Sandbox Launcher (run_tier2_sandboxed.ps1)
t6_1 = { status = "pending", commit_sha = "", description = "Create the launcher skeleton (restricted token, Job Object)" }
t6_2 = { status = "pending", commit_sha = "", description = "User Manual Verification (Phase 6)" }
# Phase 7: Git Hooks
t7_1 = { status = "pending", commit_sha = "", description = "Create pre-push hook (refuses all pushes)" }
t7_2 = { status = "pending", commit_sha = "", description = "Create post-checkout hook (detection only)" }
# Phase 8: Opt-in Tests
t8_1 = { status = "pending", commit_sha = "", description = "Add tier2_sandbox and tier2_smoke markers to pyproject.toml" }
t8_2 = { status = "pending", commit_sha = "", description = "Create the trivial smoke track (spec + plan)" }
t8_3 = { status = "pending", commit_sha = "", description = "Create test_tier2_setup_bootstrap.py (opt-in, -WhatIf)" }
t8_4 = { status = "pending", commit_sha = "", description = "Create test_tier2_sandbox_enforcement.py (opt-in, pre-push hook)" }
t8_5 = { status = "pending", commit_sha = "", description = "Create test_tier2_smoke_e2e.py (opt-in, double gate)" }
t8_6 = { status = "pending", commit_sha = "", description = "User Manual Verification (Phase 8)" }
# Phase 9: User Guide + Final Verification
t9_1 = { status = "pending", commit_sha = "", description = "Create the user guide (docs/guide_tier2_autonomous.md)" }
t9_2 = { status = "pending", commit_sha = "", description = "Update conductor/tracks.md with the new track" }
t9_3 = { status = "pending", commit_sha = "", description = "Create metadata.json (already committed 2026-06-16 in commit 6a26713d)" }
t9_4 = { status = "pending", commit_sha = "", description = "Final User Manual Verification (full track)" }
[verification]
# Filled as phases complete. The metadata.json's verification_criteria is the source of truth.
phase_1_failcount_tests_pass = false
phase_2_report_writer_tests_pass = false
phase_3_slash_command_spec_pass = false
phase_4_cli_entry_point_runs = false
phase_5_bootstrap_whatif_works = false
phase_6_sandbox_launcher_runs = false
phase_7_git_hooks_installed = false
phase_8_optin_tests_pass = false
phase_9_user_guide_complete = false
default_pytest_app_focused = false
optin_sandbox_tests_under_env_var = false
optin_smoke_tests_under_double_env_var = false
metadata_json_valid = true
[test_progress]
# Track the test count as the track progresses
failcount_unit_tests_target = 13
failcount_unit_tests_passing = 0
slash_command_spec_tests_target = 11
slash_command_spec_tests_passing = 0
report_writer_tests_target = 4
report_writer_tests_passing = 0
bootstrap_tests_target = 1
bootstrap_tests_passing = 0
sandbox_enforcement_tests_target = 1
sandbox_enforcement_tests_passing = 0
smoke_e2e_tests_target = 1
smoke_e2e_tests_passing = 0
[enforcement_stack]
# The 3-layer enforcement contract that must be verified at the end
git_push_ban_enforced = false
git_checkout_ban_enforced = false
git_restore_ban_enforced = false
git_reset_ban_enforced = false
filesystem_boundary_enforced = false
pre_push_hook_installed = false
post_checkout_hook_installed = false
opencode_deny_rules_in_clone = false
windows_restricted_token_acquired = false